Alan Stern wrote:
> This patch (as857) modifies the SG_GET_RESERVED_SIZE and
> SG_SET_RESERVED_SIZE ioctls in the sg driver, capping the values at
> the device's request_queue's max_sectors value. This will permit
> cdrecord to obtain a legal value for the maximum transfer length,
> fixing Bugzill
Doug:
I haven't gotten any feedback on this patch:
http://marc.theaimsgroup.com/?l=linux-scsi&m=117198739722640&w=2
Pending Mike's efforts to get a completely realistic estimate for the
maximum allowable size of a transfer request, is there any reason not to
accept the patch in its original form
Mike Christie wrote:
> Yeah you are right getting memory is not a problem I replied about that
> in the other mail. You do not have to use it, but the min of the
> reserved buffer and max_sectors or max_hw_sectors could still be off for
> drivers that do not support clustering or if there is a weir
On Tue, 20 Feb 2007, Mike Christie wrote:
> Yeah you are right getting memory is not a problem I replied about that
> in the other mail. You do not have to use it, but the min of the
> reserved buffer and max_sectors or max_hw_sectors could still be off for
> drivers that do not support clustering
Alan Stern wrote:
> On Tue, 20 Feb 2007, Mike Christie wrote:
>
>> I think you actually want max_hw_sectors. Well, you might and you might
>> not :)
>
> I think we do not. We don't care about the maximum transfer length the
> driver can theoretically support; we care about the maximum transfer
>
On Tue, 20 Feb 2007, Mike Christie wrote:
> I think you actually want max_hw_sectors. Well, you might and you might
> not :)
I think we do not. We don't care about the maximum transfer length the
driver can theoretically support; we care about the maximum transfer
length the system will allow.
Mike Christie wrote:
>
> The problem is that we assume we will get nice large segments. When
> using sg it will try to allocate multiple pages and make large segments.
> We could hit a bad case where we cannot allocate enough large segments,
> so a worst case would result in a max_segment_size of
Alan Stern wrote:
> This patch (as857) modifies the SG_GET_RESERVED_SIZE and
> SG_SET_RESERVED_SIZE ioctls in the sg driver, capping the values at
> the device's request_queue's max_sectors value. This will permit
> cdrecord to obtain a legal value for the maximum transfer length,
> fixing Bugzill
This patch (as857) modifies the SG_GET_RESERVED_SIZE and
SG_SET_RESERVED_SIZE ioctls in the sg driver, capping the values at
the device's request_queue's max_sectors value. This will permit
cdrecord to obtain a legal value for the maximum transfer length,
fixing Bugzilla #7026.
The patch also cap
9 matches
Mail list logo